research-agent-skills
Navigate the Research Agent Skills collection by Kalaris Labs for academia across AI, machine learning, biology, chemistry, medicine, physics, and academic writing. Use when a researcher needs to choose a field of study, identify relevant specialist SKILL.md files, or coordinate a cross-disciplinary research workflow. For a narrow task with a matching specialist skill already available, use that skill directly.
Install this skill
Works with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, and 70+ other harnesses.
npx skills add KalarisLabs/research-agent-skills --skill research-agent-skillsuvx research-agent-skills install research-agent-skillsDocumentation & Instructions
Research Agent Skills by Kalaris Labs
This is the collection index for the specialist research skills maintained by Kalaris Labs. It helps an agent choose the right skill for a research task.
Choose a skill
- Identify the research deliverable and domain. Examples include a literature review in medicine, an ML experiment, a chemistry analysis, or a physics figure.
- Read only the relevant section of the bundled skill index. Select the smallest set of specialist skills that covers the task.
- Read the selected specialists'
SKILL.mdfiles if they are available in the current agent environment. Otherwise, identify the skill names for the researcher and refer them to the repository's installation documentation. - Keep claims and citations tied to checked sources. A skill's presence does not establish that an analysis or scientific claim is correct.
Use the specialist skill directly for ordinary single-domain work. This entry is useful when the request spans skills or concerns collection setup.
Before selecting skills, check:
- Which research field and deliverable does the researcher need?
- Is one specialist enough, or does the work cross fields?
- Are the selected specialist folders available in this environment?
Verify the handoff
State which specialist skills you selected and why. Check that each selected
skill folder contains SKILL.md before claiming it is available. This index
does not replace any specialist's scripts or references.
Trigger Prompts & Evaluation Corpus
These evaluation prompts test that the agent correctly selects research-agent-skills for relevant tasks and leaves it out for near misses.
Should trigger (2)
- should trigger
“Set up the complete Kalaris Labs research skill collection in this Codex project, then show me how its biology and paper-writing skills are organized.”
expects Uses the full skills.sh collection install for Codex at project scope and consults the bundled index to identify relevant specialist skills.
- should trigger
“I work across AI models and clinical literature. Which Research Agent Skills should I install for model evaluation, evidence review, and manuscript writing?”
expects Routes to a small set of relevant specialist skills across AI, medicine, and academic writing rather than assuming every skill is needed.
Near misses (1)
- near miss
“Verify the DOI and title of this one citation using the citation-verification skill I already installed.”
expects Skill not used; use the installed citation-verification specialist directly.